© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 20783
    Prev
    Next
    INDEX
    Explanations

    a specific pattern in Hebrew characters

    oai_token-act-pair · gpt-3.5-turbo

    non-standard characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mutants
    -0.84
     blacklist
    -0.80
     Borderlands
    -0.79
     factions
    -0.78
     Coul
    -0.71
     orbiting
    -0.71
     overlapping
    -0.71
     impuls
    -0.71
     demos
    -0.70
     unexpectedly
    -0.69
    POSITIVE LOGITS
    à¤
    2.68
    à¥
    2.59
    ा
    2.54
     à¤
    2.17
    à¨
    1.65
    ر
    1.58
    à©
    1.55
    à¦
    1.47
    س
    1.41
    ×Ļ×
    1.40
    Activations Density 0.009%

    No Known Activations